Knowledge graph integration of clustered medicinal plants, molecules, diseases, and targets.

Knowledge graphs have emerged as a powerful dynamic knowledge representation model for predicting hidden patterns and relationships in medical and healthcare domains for medical diagnosis and disease prediction. However, generating, constructing, and integrating knowledge graphs for this domain is still challenging research area for such heterogeneous domain. In this paper, a framework for automatic disease knowledge graph (KG) construction and intelligent ontology integration with standard human disease ontology (DO) is developed. A major component of this framework is developing an enhanced diseases' knowledge graph that is based on collecting medical facts from medical platforms and social networks, including symptoms, causes, risk factors and prevention factors. This knowledge graph represents a major base for intelligent diagnosis and disease prediction systems. The developed disease knowledge graph includes diseases' symptoms, causes, risk factors and prevention factors and integrated with DO by more than 400 diseases. The knowledge graph presented is a step not only towards building an enriched knowledge graph for professional staff and normal users. The graph is also a step towards integrating two standard ontologies human disease and symptom ontologies that are not linked or integrated till now.

Semantic data integration provides the ability to interrelate and analyze information from multiple heterogeneous resources. With the growing complexity of medical ontologies and the big data generated from different resources, there is a need for integrating medical ontologies and finding relationships between distinct concepts from different ontologies where these concepts have logical medical relationships. Standardized Medical Ontologies are explicit specifications of shared conceptualization, which provide predefined medical vocabulary that serves as a stable conceptual interface to medical data sources. Intelligent Healthcare systems such as disease prediction systems require a reliable knowledge base that is based on Standardized medical ontologies. Knowledge graphs have emerged as a powerful dynamic representation of a knowledge base. In this paper, a framework is proposed for automatic knowledge graph generation integrating two medical standardized ontologies- Human Disease Ontology (DO), and Symptom Ontology (SYMP) using a medical online website and encyclopedia. The framework and methodologies adopted for automatically generating this knowledge graph fully integrated the two standardized ontologies. The graph is dynamic, scalable, easily reproducible, reliable, and practically efficient. A subgraph for cancer terms is also extracted and studied for modeling and representing cancer diseases, their symptoms, prevention, and risk factors.

The ‘reading to cognition gaps’ and the ‘knowledge to action gaps’ for a physician or a care provider are the root causes of patient harm and the low- value healthcare. Rule-based symptom-checkers often fail when there are multiple co-occurring symptoms. To ensure patient safety and value-based care we have constructed nine AI-driven and evidence based interconnected holistic knowledge graphs covering the entire spectrum of medical knowledge starting from symptoms to therapeutics. These knowledge graphs are in fact the digital twin of all physicians’ brains. These nine knowledge graphs are Symptomatomics, Diseasomics, SNOMED CT, Disease-Gene Network, Multimorbidity, Resistomics, Patholomics, Oncolomics, and Drugomics. These knowledge graphs are constructed from semantic integration of biomedical ontologies like Disease Ontology, Symptom Ontology, Gene Ontology, Drug Ontology, NCI Thesaurus, DisGenomics Network, PharmGKB, ChEBI, WHO AWaRe, and WHOCC. This is further enhanced through thematic integration of the knowledge mined from PubMed, DailyMed, FAERS, Wikipedia and patient data (EHR) from hospitals and cancer registry. These knowledge graphs are interconnected through common vocabularies like SNOMED CT, ICD10, ICDO, UMLS, NCIT, DOID, HGNC, GO, LOINC, ATC, RXCUI, and RxNORM codes that helped us to construct a complete clinical, medical, therapeutic, and conflicting medication knowledge graph with 723,801 nodes and 10,657,694 edges. This knowledge graph is stored in a Neo4j property graph database which is deployed in the cloud accessible 24×7 through REST/JSON-RPC and AIoT API. On top of this integrated knowledge graph we used node2vec to construct digital triplet discovering many unknown and hidden knowledge. This integrated clinical & biomedical knowledge functions as the digital twin of all physicians’ brains.KeywordsPhysicians’ brain digital twinDigital tripletSymptomatomicsDiseasomicsResistomicsPatholomicsDisGenomicsOncolomicsDrugomicsKnowledge graphHealthcare ecosystem crisisPatient safety

This paper introduces an information retrieval model that leverages knowledge graphs, specifically tailored for Clinical Trials. In these scenarios, the document in question takes the form of a semi-structured clinical trial, containing details about enrolled patients, descriptions of experiments and procedures conducted during the trial, relevant diseases, and specific enrollment criteria. While the document retains a semi-structured format, the majority of the information is expressed in natural language. Queries in this context consist of specific patient characteristics, such as disease type, genetic information, and demographic data. The primary aim of this paper is to develop and utilize a knowledge graph capable of storing this information, including links to external resources like the Disease Ontology. We propose an Object-Relational model, which is then transformed into a knowledge graph. This graph is subsequently employed to identify semantic connections between concepts present in the clinical trials and those in the queries. These connections are then utilized to formulate a retrieval model for each aspect of the query. To achieve this, we design a relevance formula that incorporates weights to account for ontological relationships between concepts. We evaluate the effectiveness of our model by comparing the results with manual annotations.

Physicians establish diagnosis by assessing a patient's signs, symptoms, age, sex, laboratory test findings and the disease history. All this must be done in limited time and against the backdrop of an increasing overall workload. In the era of evidence-based medicine it is utmost important for a clinician to be abreast of the latest guidelines and treatment protocols which are changing rapidly. In resource limited settings, the updated knowledge often does not reach the point-of-care. This paper presents an artificial intelligence (AI)-based approach for integrating comprehensive disease knowledge, to support physicians and healthcare workers in arriving at accurate diagnoses at the point-of-care. We integrated different disease-related knowledge bodies to construct a comprehensive, machine interpretable diseasomics knowledge-graph that includes the Disease Ontology, disease symptoms, SNOMED CT, DisGeNET, and PharmGKB data. The resulting disease-symptom network comprises knowledge from the Symptom Ontology, electronic health records (EHR), human symptom disease network, Disease Ontology, Wikipedia, PubMed, textbooks, and symptomology knowledge sources with 84.56% accuracy. We also integrated spatial and temporal comorbidity knowledge obtained from EHR for two population data sets from Spain and Sweden respectively. The knowledge graph is stored in a graph database as a digital twin of the disease knowledge. We use node2vec (node embedding) as digital triplet for link prediction in disease-symptom networks to identify missing associations. This diseasomics knowledge graph is expected to democratize the medical knowledge and empower non-specialist health workers to make evidence based informed decisions and help achieve the goal of universal health coverage (UHC). The machine interpretable knowledge graphs presented in this paper are associations between various entities and do not imply causation. Our differential diagnostic tool focusses on signs and symptoms and does not include a complete assessment of patient's lifestyle and health history which would typically be necessary to rule out conditions and to arrive at a final diagnosis. The predicted diseases are ordered according to the specific disease burden in South Asia. The knowledge graphs and the tools presented here can be used as a guide.

BackgroundData integration to build a biomedical knowledge graph is a challenging task. There are multiple disease ontologies used in data sources and publications, each having its hierarchy. A common task is to map between ontologies, find disease clusters and finally build a representation of the chosen disease area. There is a shortage of published resources and tools to facilitate interactive, efficient and flexible cross-referencing and analysis of multiple disease ontologies commonly found in data sources and research.ResultsOur results are represented as a knowledge graph solution that uses disease ontology cross-references and facilitates switching between ontology hierarchies for data integration and other tasks.ConclusionsGrakn core with pre-installed “Disease ontologies for knowledge graphs” facilitates the biomedical knowledge graph build and provides an elegant solution for the multiple disease ontologies problem.

1999-LB: GenomicKB—A Knowledge Graph for Human Genomic Data to Advance Understanding of Diabetes

Safe drug recommendation systems play a crucial role in minimizing adverse drug reactions and enhancing patient safety. In this research, we propose an innovative approach to develop a safety drug recommendation system by integrating the Salp Swarm Optimization-based Particle Swarm Optimization (SalpPSO) with the GraphSAGE algorithm. The goal is to optimize the hyper parameters of GraphSAGE, enabling more accurate drug-drug interaction prediction and personalized drug recommendations. The research begins with data collection from real-world datasets, including MIMIC-III, Drug Bank, and ICD-9 ontology. The databases provide comprehensive and diverse clinical data related to patients, diseases, and drugs, forming the foundation of a knowledge graph. It represents drug-related entities and their relationships, such as drugs, indications, adverse effects, and drug-drug interactions. The knowledge graph’s integration of patient data, disease ontology, and drug information enhances the system’s accuracy to predict drug-drug interactions as well as identifying potential detrimental drug reactions. The GraphSAGE algorithm is employed as the base model for learning node embeddings in the knowledge graph. To enhance its performance, we propose the SalpPSO algorithm for hyper parameter optimization. SalpPSO combines features from Salp Swarm Optimization and Particle Swarm Optimization, offering a robust and effective optimization process. The optimized hyper parameters lead to more reliable and accurate drug recommendation system. For evaluation, the dataset is split into training and validation sets and compared the performance of the modified GraphSAGE model with SalpPSO-optimized hyper parameters to the standard models. The experimental analysis conducted in terms of various measures proves the efficiency of the proposed safe recommendation system, offering valuable for healthcare experts in making more informed and personalized drug treatment decisions for patients.

BackgroundPreeclampsia (PE) is a serious hypertensive complication during pregnancy characterized by immune dysregulation and vascular dysfunction, however, the precise molecular mechanisms and effective therapeutic strategies remain unclear. This study focused on identifying immune-related differentially expressed genes (IRDEGs) in PE, investigate their biological significance and regulatory networks, and establish robust diagnostic models through integrated bioinformatics and experimental analyses.MethodsGene expression data from the GSE75010 dataset were analyzed utilizing the R-based "limma" package to determine differentially expressed genes (DEGs), which were intersected with immune-related genes (IRGs) to obtain IRDEGs. Functional enrichment was assessed using Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and Disease Ontology (DO) analyses. Hub genes were identified via Random Forest (RF) and LASSO regression algorithms, and their diagnostic performance was assessed via receiver operating characteristic (ROC) curve evaluation in both training (GSE75010) and validation (GSE44711) cohorts. Immune cell composition and its association with hub genes were explored using CIBERSORT. Regulatory networks, including protein–protein interaction (PPI), mRNA-miRNA and mRNA-TF interactions, were constructed using ENCORI and CHIPBase databases. Analysis of potential pharmaceutical-gene interactions was performed via DGIdb platform interrogation, followed by experimental validation in placental tissue and trophoblast cells.ResultsWe identified 354 DEGs, including 49 IRDEGs (25 upregulated and 24 downregulated). Enrichment evaluation demonstrated that IRDEGs were associated with PI3K-AKT signaling, chemokine signaling, and cytokine-cytokine receptor interaction. DO analysis linked IRDEGs to PE, cardiovascular diseases, and reproductive disorders. Four hub genes (FLT1, PIK3CB, KLRD1, and APLN) were identified as PE biomarkers based on their connectivity in the PPI network and performance in machine learning models. The RF-based diagnostic model demonstrated excellent discrimination ability with AUCs of 0.9468 (training cohort) and 0.9844 (validation cohort). Immune infiltration analysis revealed higher levels of eosinophils, plasma cells, and CD8 + T cells in PE, while monocytes and M2 macrophages were reduced. Notably, hub genes showed distinct correlations with immune cell subtypes, such as the positive association observed between FLT1 and plasma cells, contrasting with the inverse relationship documented between APLN and CD8 + T cells. Network analysis identified 128 mRNA-miRNA and 31 mRNA-TF interaction pairs. Drug-gene interaction analysis showed cyclooxygenase inhibitors, such as aspirin, targeted APLN, while TNF-α inhibitors, such as etanercept, targeted KLRD1. Experimental validation confirmed consistent expression trends across clinical specimens and in vitro models: FLT1 and PIK3CB were significantly upregulated while KLRD1 and APLN were significantly downregulated in both preeclamptic placental tissues and hypoxia-exposed trophoblast cells.ConclusionsOur study identified four hub IRDEGs that may serve as potential diagnostic indicators and therapeutic targets for PE. These findings suggest an important role of immune dysregulation in PE pathogenesis and offer new perspectives for treatment strategies. By integrating computational predictions with experimental evidence, our work contributes to the foundation for future clinical applications, though further research including early-stage PE is needed to validate these observations.Supplementary InformationThe online version contains supplementary material available at 10.1186/s12884-025-08169-9.

BackgroundUnderstanding the impact of gene interactions on disease phenotypes is increasingly recognised as a crucial aspect of genetic disease research. This trend is reflected by the growing amount of clinical research on oligogenic diseases, where disease manifestations are influenced by combinations of variants on a few specific genes. Although statistical machine-learning methods have been developed to identify relevant genetic variant or gene combinations associated with oligogenic diseases, they rely on abstract features and black-box models, posing challenges to interpretability for medical experts and impeding their ability to comprehend and validate predictions. In this work, we present a novel, interpretable predictive approach based on a knowledge graph that not only provides accurate predictions of disease-causing gene interactions but also offers explanations for these results.ResultsWe introduce BOCK, a knowledge graph constructed to explore disease-causing genetic interactions, integrating curated information on oligogenic diseases from clinical cases with relevant biomedical networks and ontologies. Using this graph, we developed a novel predictive framework based on heterogenous paths connecting gene pairs. This method trains an interpretable decision set model that not only accurately predicts pathogenic gene interactions, but also unveils the patterns associated with these diseases. A unique aspect of our approach is its ability to offer, along with each positive prediction, explanations in the form of subgraphs, revealing the specific entities and relationships that led to each pathogenic prediction.ConclusionOur method, built with interpretability in mind, leverages heterogenous path information in knowledge graphs to predict pathogenic gene interactions and generate meaningful explanations. This not only broadens our understanding of the molecular mechanisms underlying oligogenic diseases, but also presents a novel application of knowledge graphs in creating more transparent and insightful predictors for genetic research.

ARCH: Large-scale knowledge graph via aggregated narrative codified health records analysis.

The cost of drug development continues to rise and may be prohibitive in cases of unmet clinical need, particularly for rare diseases. Artificial intelligence-based methods are promising in their potential to discover new treatment options. The task of drug repurposing hypothesis generation is well-posed as a link prediction problem in a knowledge graph (KG) of interacting of drugs, proteins, genes and disease phenotypes. KGs derived from biomedical literature are semantically rich and up-to-date representations of scientific knowledge. Inference methods on scientific KGs can be confounded by unspecified contexts and contradictions. Extracting context enables incorporation of relevant pharmacokinetic and pharmacodynamic detail, such as tissue specificity of interactions. Contradictions in biomedical KGs may arise when contexts are omitted or due to contradicting research claims. In this review, we describe challenges to creating literature-scale representations of pharmacological knowledge and survey current approaches toward incorporating context and resolving contradictions.

Citizens in developing countries rely on indigenous knowledge and practices and use locally available medicinal plants for different treatments. Due to limited instrumentation for chemical and biological characterization, most studies investigating the bioactive properties of Sri Lankan medicinal plants rarely progress to the molecular level. While for some plants, the whole plant extracts have been tested, most of the individual active compounds and their effect mechanisms have still not been identified. The separation of bioactive compounds from natural sources is a challenging task. Multi‐imaging high‐performance thin‐layer chromatography (HPTLC‐UV/Vis/FLD) combined with biological/biochemical assays (effect‐ directed analysis, EDA) and high‐resolution mass spectrometry (HRMS) provide the straightforward identification of natural products without prior tedious fractionation and compound isolation. Separating complex plant extracts into individual compounds, and still on the same adsorbent surface, studying their effects highlighted their potential. These findings can be used to substantiate current traditional medicinal knowledge and to evaluate their benefits, risks, and limitations. The developed hyphenated HPTLC‐UV/Vis/FLD‐EDA‐HESI‐ HRMS methods for identification of single compound effects in Sri Lankan Abelmoschus moschatus and Cinnamomum zeylanicum included (1) non‐target screening, (2) assignment of prominent individual bioactive compounds, and (3) comparison of product profiles to check the quality of commercial products. Both studies revealed not only the phytochemical profiles but also prioritized bioactive constituents. Diverse antimicrobials, antioxidants, and inhibitors of glucosidase, tyrosinase, and cholinesterase were detected. Running reference standards in parallel to identified compounds, confirmed the assignments and bioactivities. The sustainable and environmentally friendly technique can be used in developing countries for profiling and valorization of plant‐based preparations.

The suddenness of landslide disasters often causes significant loss of life and property. Accurate assessment of landslide disaster susceptibility is of great significance in enhancing the ability of accurate disaster prevention. To address the problems of strong subjectivity in the selection of assessment indicators and low efficiency of the assessment process caused by the insufficient application of a priori knowledge in landslide susceptibility assessment, in this paper, we propose a novel landslide susceptibility assessment framework by combing domain knowledge graph and machine learning algorithms. Firstly, we combine unstructured data, extract priori knowledge based on the Unified Structure Generation for Universal Information Extraction Pre-trained model (UIE) fine-tuned with a small amount of labeled data to construct a landslide susceptibility knowledge graph. We use Paired Relation Vectors (PairRE) to characterize the knowledge graph, then construct a target area characterization factor recommendation model by calculating spatial correlation, attribute similarity, Term Frequency–Inverse Document Frequency (TF-IDF) metrics. We select the optimal model and optimal feature combination among six typical machine learning (ML) models to construct interpretable landslide disaster susceptibility assessment mapping. Experimental validation and analysis are carried out on the three gorges area (TGA), and the results show the effectiveness of the feature factors recommended by the knowledge graph characterization learning, with the overall accuracy of the model after adding associated disaster factors reaching 87.2%. The methodology proposed in this research is a better contribution to the knowledge and data-driven assessment of landslide disaster susceptibility.

Tables and structured lists on Web pages are a potential source of valuable information, and several methods have been proposed to annotate them with semantics that can be leveraged for search, question answering and information extraction. This paper is concerned with the specific problem of finding and ranking relations from a given Knowledge Graph (KG) that hold over pairs of entities juxtaposed in a table or structured list. The state-of-the-art for this task is to attempt to link the entities mentioned in the table cells to objects in the KG and rank the relations that hold for those linked objects. As a result, these methods are hampered by the incompleteness and uneven coverage in even the best knowledge graphs available today. The alternative described here does not require entity linking, relying instead on ranking relations using generative language models derived from Web-scale corpora. As such, it can produce quality results even when the entities in the table are missing in the KG. The experimental validation, designed to expose the challenges posed by KG incompleteness, shows that our approach is robust and effective in practice.